The hospital room smelled of disinfectant and failure. Liam, usually a picture of vibrant health, felt utterly drained. The mix-up – his records exchanged with a chain smoker who had a penchant for late nights and fried food - had brought his world crumbling down. He should be running, training for his next marathon. Now, he was being warned about the potential risks.

He glared at the nurse, who was offering reassurances that sounded more like platitudes. He felt a deep aversion to the entire situation. He didn't want the sympathy, the pity, the condescending advice. He didn't want anything to do with this mess.

He turned his head away, staring out the window at the bleak landscape. The other patient’s lifestyle – his habits – his very existence seemed like a personal insult. He would fight this. He'd correct the injustice.

Emotion: contemptuous

Cluster: Anger / Hostility
PC1 (Valence): -0.40 Negative
PC2 (Disposition): 2.07

Role in Research

This story is one of 1,000 stories generated for the emotion contemptuous. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 contemptuous stories, after denoising with neutral dialogue baselines, produces the contemptuous emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the contemptuous vector is projected through the unembedding matrix.

Promoted:
C0.502
l0.423
fact0.287
either0.265
👎0.262
Suppressed:
own-0.367
unexpectedly-0.303
serendip-0.265
Suddenly-0.253
previously-0.250